Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 103 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0003

Data Index: 171974 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0622. Min Act: -0.0003

Data Index: 849568 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0589. Min Act: -0.0002

Data Index: 717928 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0589. Min Act: -0.0003

Data Index: 968899 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0563. Min Act: -0.0003

Data Index: 307742 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1095754 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0568. Min Act: -0.0003

Data Index: 86522 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0573. Min Act: -0.0003

Data Index: 758002 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0554. Min Act: -0.0003

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0561. Min Act: -0.0003

Data Index: 381836 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0539. Min Act: -0.0002

Data Index: 55755 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1165752 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1260113 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0547. Min Act: -0.0002

Data Index: 562576 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0541. Min Act: -0.0003

Data Index: 871695 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0548. Min Act: -0.0001

Data Index: 321181 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1185782 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0537. Min Act: -0.0003

Data Index: 76377 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0543. Min Act: -0.0003

Data Index: 226313 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0548. Min Act: -0.0003

Data Index: 25417 (C4 (Web Text))

Max Activating Token Index: 475